# Guide: Stream Anthropic responses using the message-per-token pattern

This guide shows you how to stream AI responses from Anthropic's [Messages API](https://docs.anthropic.com/en/api/messages) over Ably using the [message-per-token pattern](https://ably.com/docs/ai-transport/token-streaming/message-per-token.md). Specifically, it implements the [explicit start/stop events approach](https://ably.com/docs/ai-transport/token-streaming/message-per-token.md#explicit-events), which publishes each response token as an individual message, along with explicit lifecycle events to signal when responses begin and end.

Using Ably to distribute tokens from the Anthropic SDK enables you to broadcast AI responses to thousands of concurrent subscribers with reliable message delivery and ordering guarantees, ensuring that each client receives the complete response stream with all tokens delivered in order. This approach decouples your AI inference from client connections, enabling you to scale agents independently and handle reconnections gracefully.

<Aside data-type="further-reading">
To discover other approaches to token streaming, including the [message-per-response](https://ably.com/docs/ai-transport/token-streaming/message-per-response.md) pattern, see the [token streaming](https://ably.com/docs/ai-transport/token-streaming.md) documentation.
</Aside>

## Prerequisites 

To follow this guide, you need:
- Node.js 20 or higher
- An Anthropic API key
- An Ably API key

Useful links:
- [Anthropic API documentation](https://docs.anthropic.com/en/api)
- [Ably JavaScript SDK getting started](https://ably.com/docs/getting-started/javascript.md)

Create a new NPM package, which will contain the publisher and subscriber code:

<Code>
```shell
mkdir ably-anthropic-example && cd ably-anthropic-example
npm init -y
```
</Code>

Install the required packages using NPM:

<Code>
```shell
npm install @anthropic-ai/sdk@^0.71 ably@^2
```
</Code>

<Aside data-type="note">
This guide uses version 0.71.x of the Anthropic SDK. Some details of interacting with the Anthropic SDK may differ from those given here if using a different major version.
</Aside>

Export your Anthropic API key to the environment, which will be used later in the guide by the Anthropic SDK:

<Code>
```shell
export ANTHROPIC_API_KEY="your_api_key_here"
```
</Code>

## Step 1: Get a streamed response from Anthropic 

Initialize an Anthropic client and use the [Messages API](https://docs.anthropic.com/en/api/messages) to stream model output as a series of events.

Create a new file `publisher.mjs` with the following contents:

<Code>
```javascript
import Anthropic from '@anthropic-ai/sdk';

// Initialize Anthropic client
const anthropic = new Anthropic();

// Process each streaming event
function processEvent(event) {
  console.log(JSON.stringify(event));
  // This function is updated in the next sections
}

// Create streaming response from Anthropic
async function streamAnthropicResponse(prompt) {
  const stream = await anthropic.messages.create({
    model: "claude-sonnet-4-5",
    max_tokens: 1024,
    messages: [{ role: "user", content: prompt }],
    stream: true,
  });

  // Iterate through streaming events
  for await (const event of stream) {
    processEvent(event);
  }
}

// Usage example
streamAnthropicResponse("Tell me a short joke");
```
</Code>

### Understand Anthropic streaming events 

Anthropic's Messages API [streams](https://docs.anthropic.com/en/api/messages-streaming) model output as a series of events when you set `stream: true`. Each streamed event includes a `type` property which describes the event type. A complete text response can be constructed from the following event types:

- [`message_start`](https://platform.claude.com/docs/en/build-with-claude/streaming#event-types): Signals the start of a response. Contains a `message` object with an `id` to correlate subsequent events.

- [`content_block_start`](https://platform.claude.com/docs/en/build-with-claude/streaming#event-types): Indicates the start of a new content block. For text responses, the `content_block` will have `type: "text"`; other types may be specified, such as `"thinking"` for internal reasoning tokens. The `index` indicates the position of this item in the message's `content` array.

- [`content_block_delta`](https://platform.claude.com/docs/en/build-with-claude/streaming#content-block-delta-types): Contains a single text delta in the `delta.text` field. If `delta.type === "text_delta"` the delta contains model response text; other types may be specified, such as `"thinking_delta"` for internal reasoning tokens. Use the `index` to correlate deltas relating to a specific content block.

- [`content_block_stop`](https://platform.claude.com/docs/en/build-with-claude/streaming#event-types): Signals completion of a content block. Contains the `index` that identifies content block.

- [`message_delta`](https://platform.claude.com/docs/en/build-with-claude/streaming#event-types): Contains additional message-level metadata that may be streamed incrementally. Includes a [`delta.stop_reason`](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons) which indicates why the model successfully completed its response generation.

- [`message_stop`](https://platform.claude.com/docs/en/build-with-claude/streaming#event-types): Signals the end of the response.

The following example shows the event sequence received when streaming a response:

<Code>
```json
// 1. Message starts
{"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_016hhjrqVK4rCZ2uEGdyWfmt","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":12,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}}}

// 2. Content block starts
{"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}

// 3. Text tokens stream in as delta events
{"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Why"}}
{"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" don't scientists trust atoms?\n\nBecause"}}
{"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" they make up everything!"}}

// 4. Content block completes
{"type":"content_block_stop","index":0}

// 5. Message delta (usage stats)
{"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":12,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":17}}

// 6. Message completes
{"type":"message_stop"}
```
</Code>

<Aside data-type="note">
This is only an illustrative example for a simple "text in, text out" use case and may not reflect the exact sequence of events that you observe from the Anthropic API. It also does not describe response generation errors or refusals. For complete details on all event types and their properties, see [Anthropic Streaming events](https://docs.anthropic.com/en/api/messages-streaming).
</Aside>

## Step 2: Publish streaming events to Ably 

Publish Anthropic streaming events to Ably to reliably and scalably distribute them to subscribers.

This implementation follows the [explicit start/stop events pattern](https://ably.com/docs/ai-transport/token-streaming/message-per-token.md#explicit-events), which provides clear response boundaries.

### Initialize the Ably client 

Add the Ably client initialization to your `publisher.mjs` file:

<Code>
```javascript
import Ably from 'ably';

// Initialize Ably Realtime client
const realtime = new Ably.Realtime({
  key: 'your-api-key',
  echoMessages: false
});

// Create a channel for publishing streamed AI responses
const channel = realtime.channels.get('your-channel-name');
```
</Code>

The Ably Realtime client maintains a persistent connection to the Ably service, which allows you to publish tokens at high message rates with low latency.

<Aside data-type="note">
Set [`echoMessages`](https://ably.com/docs/api/realtime-sdk/types.md#client-options) to `false` on the agent's Ably client to prevent the agent from receiving its own streamed tokens, avoiding billing for [echoed messages](https://ably.com/docs/pub-sub/advanced.md#echo).
</Aside>

### Map Anthropic streaming events to Ably messages 

Choose how to map [Anthropic streaming events](#understand-streaming-events) to Ably [messages](https://ably.com/docs/messages.md). You can choose any mapping strategy that suits your application's needs. This guide uses the following pattern as an example:

- `start`: Signals the beginning of a response
- `token`: Contains the incremental text content for each delta
- `stop`: Signals the completion of a response

<Aside data-type="note">
This implementation assumes each response contains a single text content block. For production use cases with multiple content blocks or concurrent responses, consider tracking state per message ID and content block index.
</Aside>

Update your `publisher.mjs` file to initialize the Ably client and update the `processEvent()` function to publish events to Ably:

<Code>
```javascript
// Track state across events
let responseId = null;

// Process each streaming event and publish to Ably
function processEvent(event) {
  switch (event.type) {
    case 'message_start':
      // Capture message ID when response starts
      responseId = event.message.id;

      // Publish start event
      channel.publish({
        name: 'start',
        extras: {
          headers: { responseId }
        }
      });
      break;

    case 'content_block_delta':
      // Publish tokens from text deltas only
      if (event.delta.type === 'text_delta') {
        channel.publish({
          name: 'token',
          data: event.delta.text,
          extras: {
            headers: { responseId }
          }
        });
      }
      break;

    case 'message_stop':
      // Publish stop event when response completes
      channel.publish({
        name: 'stop',
        extras: {
          headers: { responseId }
        }
      });
      break;
  }
}
```
</Code>

This implementation:

- Publishes a `start` event when the response begins
- Filters for `content_block_delta` events with `text_delta` type and publishes them as `token` events
- Publishes a `stop` event when the response completes
- All published events include the `responseId` in message [`extras`](https://ably.com/docs/messages.md#properties) to allow the client to correlate events relating to a particular response

<Aside data-type="note">
This implementation publishes Ably messages without `await` to maximize throughput. Ably maintains message ordering even without awaiting each publish. For more information, see [Publishing tokens](https://ably.com/docs/ai-transport/token-streaming/message-per-token.md#publishing).
</Aside>

Run the publisher to see tokens streaming to Ably:

<Code>
```shell
node publisher.mjs
```
</Code>

## Step 3: Subscribe to streaming tokens 

Create a subscriber that receives the streaming events from Ably and reconstructs the response.

Create a new file `subscriber.mjs` with the following contents:

<Code>
```javascript
import Ably from 'ably';

// Initialize Ably Realtime client
const realtime = new Ably.Realtime({ key: 'your-api-key' });

// Get the same channel used by the publisher
const channel = realtime.channels.get('your-channel-name');

// Track responses by ID
const responses = new Map();

// Handle response start
await channel.subscribe('start', (message) => {
  const responseId = message.extras?.headers?.responseId;
  console.log('\n[Response started]', responseId);
  responses.set(responseId, '');
});

// Handle tokens
await channel.subscribe('token', (message) => {
  const responseId = message.extras?.headers?.responseId;
  const token = message.data;

  // Append token to response
  const currentText = responses.get(responseId) || '';
  responses.set(responseId, currentText + token);

  // Display token as it arrives
  process.stdout.write(token);
});

// Handle response stop
await channel.subscribe('stop', (message) => {
  const responseId = message.extras?.headers?.responseId;
  const finalText = responses.get(responseId);
  console.log('\n[Response completed]', responseId);
});

console.log('Subscriber ready, waiting for tokens...');
```
</Code>

Run the subscriber in a separate terminal:

<Code>
```shell
node subscriber.mjs
```
</Code>

With the subscriber running, run the publisher in another terminal. The tokens stream in realtime as the Anthropic model generates them.

## Step 4: Stream with multiple publishers and subscribers 

Ably's [channel-oriented sessions](https://ably.com/docs/ai-transport/sessions-identity.md#connection-oriented-vs-channel-oriented-sessions) enables multiple AI agents to publish responses and multiple users to receive them on a single channel simultaneously. Ably handles message delivery to all participants, eliminating the need to implement routing logic or manage state synchronization across connections.

### Broadcasting to multiple subscribers 

Each subscriber receives the complete stream of tokens independently, enabling you to build collaborative experiences or multi-device applications.

Run a subscriber in multiple separate terminals:

<Code>
```shell
# Terminal 1
node subscriber.mjs

# Terminal 2
node subscriber.mjs

# Terminal 3
node subscriber.mjs
```
</Code>

All subscribers receive the same stream of tokens in realtime.

### Publishing concurrent responses 

The implementation uses `responseId` in message [`extras`](https://ably.com/docs/messages.md#properties) to correlate tokens with their originating response. This enables multiple publishers to stream different responses concurrently on the same [channel](https://ably.com/docs/channels.md), with each subscriber correctly tracking all responses independently.

To demonstrate this, run a publisher in multiple separate terminals:

<Code>
```shell
# Terminal 1
node publisher.mjs

# Terminal 2
node publisher.mjs

# Terminal 3
node publisher.mjs
```
</Code>

All running subscribers receive tokens from all responses concurrently. Each subscriber correctly reconstructs each response separately using the `responseId` to correlate tokens.

## Next steps

- Learn more about the [message-per-token pattern](https://ably.com/docs/ai-transport/token-streaming/message-per-token.md) used in this guide
- Learn about [client hydration strategies](https://ably.com/docs/ai-transport/token-streaming/message-per-token.md#hydration) for handling late joiners and reconnections
- Understand [sessions and identity](https://ably.com/docs/ai-transport/sessions-identity.md) in AI enabled applications
- Explore the [message-per-response pattern](https://ably.com/docs/ai-transport/token-streaming/message-per-response.md) for storing complete AI responses as single messages in history